Tuesday, July 27, 2010

More Damned Lies with Statistics

The oft -heard remark "lies, damned lies, and statistics" - has been repeated so often and in such varied contexts that many people now automatically associate statistics with sophisticated lies. However, this is not so. Once any statistical test is used with honesty and responsibility, the methodology and results provide a legitimate path to further inquiry.

For example, in observing the Sun over a period of months or years, one can accumulate data on: changing sunspot area, occurrence of specific types of solar flares (e.g. different optical and morphological classes). When this data is assembled into categories (e.g. A for sunspot area, F for flare frequency etc.), and fitted statistically, it can describe a rudimentary empirical system.

If I do a linear regression to find a fit for F (flare frequency, or flares per day) vs. A(area) of a sunspot group, I may obtain a statistical function of the form:

F = A(S1) + C

where C is some quantity that intersects the particular (y-axis), in this case the one for F. This is a mathematical representation of an empirical relationship. The mathematical form is dictated by how the data fits, and is a matter of using standard statistical tests. The empirical system that results is not a matter of “belief” but simply the degree of goodness of fit for the data.

In acquiring the data via random sample, and then assembling it, a precise statistical procedure called a “least squares regression” line represents the best fit given the data points. The beauty is that once the raw data is available, and key parameters (such as r, the Pearson product-moment correlation coefficient) are known - one can easily ascertain whether any trickery is afoot.

In economics (which to be sure is not a science) it appears such cross-checks are not so common. This paves the way for egregious claims such as appeared in The Wall Street Journal's Op-ed two days ago. The editorial makes use of a table from the White House Office of Management and Budget to attempt to show the deficits were significantly less under Reagan than under Obama - and hence Reagan (with all his supply side crappola) must have been some kind of master guru at Econ.

As the editorial puts it (referencing the table - see inset image):

"Yet as the table shows the Reagan deficits never reached more than 6% of GDP and that happened only in 1983, the first year of economic recovery"

The last phrase is a reference to the 1981-82 recession. The op-ed goes on to say:

"The Obama deficits are double that, and more than one-third higher than even un der the Gipper's worst year"

Now, let's try to shed some perspective on these claims. First, the WSJ omitted a huge piece of background information: that the Reagan Administration commenced with the U.S. in the position of a global creditor nation, not debtor. It was precisely Reagan's wanton defense spending ($2.1 trillion total then or nearly $4.2 trillion in today's dollars!) that propelled the inital mammoth deficits that would become long lasting millstones around the nation's neck. Meanwhile, Obama inherited nearly 30 years of accumulated deficits with only some surplus year breaks duriing Clinton's term - made possible by take hikes in 1994.

Thus, the WSJ's comparison is somewhat like comparing a thoroughbred's performance - even after it's saddled by a 200 lb. jockey, with a tortoise's over the same furlong span. Obviously, the thoroughbred will still prevail - though the much heavier than normal jockey weight might slow him down a tad.

So, starting at $0 deficits (in 1980)is not the same as starting from a nearly $7 trillion hole as Obama did in January, 2009. No wonder then Reagan's deficit numbers are so low.

What we do know, however, is that deficits created via supply side tax cuts propagate forward in time, as the value of currency debases or inflation rises. Thus, no surprise that the actual calamity of the Reagan tax cuts wasn't felt until Bush Senior's last year in office:

James Medoff and Andrew Harless, in their book, The Indebted Society, 1995, p. 23:

"..In 1993, the year that Bush left office, the public debt was a staggering 51.9 percent of the GDP."

And realize here that this was after the senior Bush went back on his "Read my lips: No new taxes!" pledge. Thus, even his tax increase (which may have cost him re-election in 1992) wasn't adequate to control the damage done during the Reagan years, which we are still living with.

The Journal editorial also makes a false comparison between revenue as a share of GDP during the Reagan era ("never fell lower than 17.3% of GDP") and that in the Obama era ("astonishing low of 14.5% only to rise to 15.8% in 2011 even with the huge tax increase that hits on January 1, 2011")

But unmentioned by the Journal is that Reagan's revenues "never went below 17.3% of GDP" because he raided Social Security monies to conceal the size of the deficits! Meanwhile, Obama's revenue of 14.5% of GDP is actually damned good, considering what he inherited from Shrubya: not the least of which was a $2.2 trillion tax cut hole, plus a $1.1 trillion hole from military adventures and occupations.

As for "only rising to 15.8% in 2011", well give me a break already! After all, just as the tax cuts took time to inflict their calamitous budget damage, it will take time to correct it. Again, what the Journal doesn't say is more illuminating than what it does: namely that if ALL the Bush tax cuts are allowed to expire nearly $2.2 trillion will be saved by 2020. That is $2.2 trillion in deficits that might otherwise have to be taken out of Social Security (via cuts) or Medicare.

Economic statistics, in other words, can be justified for comparisons - say of the performance of two different leaders in different eras - provided they compare the same things, or make adjustments for the differing contexts. If not, then it's no more useful than comparing dust storms on Mars to tornadoes in the U.S. Midwest.

No comments: